Triple
T8563235
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcus Brody |
E202738
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Sallah |
E224931
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Sallah | Statement: [Marcus Brody, associatedWith, Sallah]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sallah Context triple: [Marcus Brody, associatedWith, Sallah]
-
A.
Sallah
chosen
Sallah is a jovial, resourceful Egyptian excavator and close ally of Indiana Jones who helps him navigate dangerous archaeological adventures.
-
B.
Hassan
Hassan is a person known primarily as the sibling of Murad Mirza.
-
C.
Hassan
Hassan is a loyal and selfless Hazara boy whose friendship with Amir and the injustices he endures form the emotional core of the film "The Kite Runner."
-
D.
Hassan
Hassan is a key antagonist in Lord Byron’s narrative poem "The Giaour," depicted as a powerful Ottoman leader whose actions drive the poem’s central conflict.
-
E.
Hassan
Hassan is a male given name of Arabic origin commonly used across the Muslim world and beyond.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca8326e6c881908ff720d6abaebdc5 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe9cfc4a48190ae4530d3614d115f |
completed | March 31, 2026, 3:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cebb84a6988190ba6852f72c8918ca |
completed | April 2, 2026, 6:55 p.m. |
Created at: March 30, 2026, 6:20 p.m.